Sydney WiMLDS Meetup 25 November 2019 -Technical Presentation
•
0 likes•50 views
The document discusses Python, natural language processing (NLP), and Alteryx. It begins with defining Python and comparing it to other programming languages. It then discusses how NLP is used in different industries and defines Alteryx, explaining how it is used and why it is popular. The document provides an agenda and learning objectives for a session on these topics.
Recommended
Recommended
More Related Content
Similar to Sydney WiMLDS Meetup 25 November 2019 -Technical Presentation
Similar to Sydney WiMLDS Meetup 25 November 2019 -Technical Presentation (20)
Recently uploaded
Recently uploaded (20)
Sydney WiMLDS Meetup 25 November 2019 -Technical Presentation
- 1. NLP – PYTHON – ALTERYX
- 2. AGENDA Define Python and compare it to other programming languages Discuss NLP and how it is used in different industries Define Alteryx, explain how it is used and why it is so popular today in the marketplace 11/25/2019 Learning Objectives 2 Disclaimer : The following slides do not reflect the opinions of my employer, but are my own personal opinions
- 4. ABOUT ME – FROM FINANCIAL PLANNING TO DATA SCIENCE 11/25/2019 4
- 5. LinkedIn post You are making progress even when you do not feel you are. Grit GFC Reskill /Retrain Be uncomfortable 11/25/2019 5 Tip of the Iceberg
- 6. ABOUT ME – NEW LIFE IN DATA SCIENCE 11/25/2019 6
- 8. WHAT IS CRISP DM? Cross Industry Standard Process for Data Mining 11/25/2019 8 ▪ Data Science ▪ Data Analytics ▪ Consulting
- 10. PYTHON Python is an open source language 11/25/2019 10
- 11. PRE-WORK DOWNLOAD PYTHON 3.7 11/25/2019 11
- 13. 11/25/2019 13 MAC Users: In Terminal, type: jupyter notebook to launch your notebook Launch Jupyter Notebook
- 14. PYTHON Reproducibility Turn your code into a slide deck for your boss Open Source Notebooks – code + output Data Visualisation Produce a report as a data analyst Deep Learning Machine Learning 11/25/2019 14
- 16. CREATE A DATABASE ENGINE IN PYTHON 11/25/2019 16
- 18. CONNECTING TO A DATABASE - PYTHON 11/25/2019 18
- 20. CHECK WHICH JOIN IS APPROPRIATE FOR YOU 11/25/2019 20 ▪ Do you want to preserve user names on the left? ▪ How will you treat N/A’s? ▪ An inner join may reduce your data points ▪ What problem are you trying to answer? https://javarevisited.blogspot.com/2012/11/how-to-join-three-tables-in-sql-query-mysql-sqlserver.html#axzz665Ch4Lx2
- 21. WRITE PYTHON FILE TO R 11/25/2019 21 Write to CSV and read into R Call Python from R Markdown ▪ https://rstudio.github.io/reticulate/
- 22. PYTHON WORD CLOUDS – TEXT DATA 11/25/2019
- 26. EXPLANATORY INSIGHTS 11/25/2019 26 Imbalanced classes – resampling methods cross validation
- 29. MODEL EVALUATION METRICS 11/25/2019 29 The confusion matrix, which is a breakdown of predictions into a table showing correct predictions and the types of incorrect predictions made. Ideally, you will only see numbers in the diagonal, which means that all your predictions were correct! ● Precision is a measure of a classifier’s exactness. The higher the precision, the more accurate the classifier. ● Recall is a measure of a classifier’s completeness. The higher the recall, the more cases the classifier covers. ● The F1 Score or F-score is a weighted average of precision and recall. ● Area under the ROC curve. Source: Udacity
- 31. NLP – UNSTRUCTURED DATA NATURAL LANGUAGE PROCESSING 11/25/2019 31
- 32. OBTAIN THE DATA 11/25/2019 32 ▪ Given a new complaint comes in, We want to assign it to one of 4 categories. The classifier makes the assumption that each new complaint is assigned to one and only one category.
- 33. WHAT IS CRISP DM? Cross Industry Standard Process for Data Mining 11/25/2019 33 Data Understanding Obtain Data
- 38. Excel on steroids Self service analytics – you do not need to code What can it do? Workflow Optimization – compress file size, speed up processing Data Preparation and Data Blending (joins) Writing fast and accurate expressions Using Macros in workflows Containers Data Parsing – Text to Columns Outputs files to csv, an Alteryx workflow and even a Tableau hyper file Predictive analytics 11/25/2019 38 ALTERYX DESIGNER
- 39. 11/25/2019 39 ▪ Open source languages Python and R do not appear in Gartner’s 2018 magic quadrant ▪ Alteryx is a ‘challenger’ in machine learning and data science Machine Learning Platforms
- 40. 11/25/2019 40 Choosing the right Alteryx Tool https://community.alteryx.com/t5/Alteryx-Community-Resources/Designer-Cheat-Sheet/ta-p/371793?attachment-id=36217
- 42. WEBSCRAPING Python and Alteryx We know you want to impress your boss and do web scraping Check firstly if your company allows you to scrape someone else’s data Speak with your business risk team You may be breaching copyright laws under some company terms and conditions Some websites are locked down by organizations 11/25/2019 42
- 44. 11/25/2019 44
- 45. 11/25/2019 45
- 47. MY TWO CENTS – DATA SCIENCE CAREER TIPS Meetup.com e.g data science, data engineering, Rladies, Sydney Women in Machine Learning and Data Science, Women who code, PyData, Docker, Kubernetes, AWS Lunch & Learn Hackathons - Data Science is a team sport Data Science community – Get Involved Data Science blogs Learn Python, R and SQL Internship 11/25/2019 47
- 48. Job Boards– Buyer Beware Ask the recruiter what duties you will be performing in your data scientist role Ask the hiring manager what your duties you will be performing in your data scientist role Do not proceed to a further interview if the hiring manager says ‘yes you will be doing reporting and we may do data science in 18 months time’ - Run for your life! Keep on applying for data science roles, get a mentor, speak to the community, do you have peace? 11/25/2019 48 Data Science Interviews Roles and responsibilities Skills & Experience
- 50. BOOKS I RECOMMEND 11/25/2019 50
- 51. HANDY RESOURCES https://github.com/REMitchell/python-scraping Tutorials Blogs Meetups Data Sets – AWS, Data.gov 11/25/2019 51
- 52. TURN JUPYTER NOTEBOOK INTO SLIDES 11/25/2019 52